Feature Extraction
Transformers
Safetensors
PyTorch
Japanese
zipformer
k2ssl
icefall
audio
speech
japanese
speech-representation-learning
self-supervised-learning
continued-pretraining
masked-prediction
acoustic-units
custom_code
arxiv:2411.17100
Instructions to use KeisukeMiyamoto/zipformer-cpt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KeisukeMiyamoto/zipformer-cpt with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="KeisukeMiyamoto/zipformer-cpt", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("KeisukeMiyamoto/zipformer-cpt", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 216 Bytes
5d82479 | 1 2 3 4 5 6 7 8 9 10 | {
"do_normalize": false,
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
"feature_size": 1,
"padding_side": "right",
"padding_value": 0.0,
"return_attention_mask": false,
"sampling_rate": 16000
}
|